Triple
T28801622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Diaoyu Castle |
E727250
|
entity |
| Predicate | MöngkeCauseOfDeath |
P15555
|
FINISHED |
| Object | wounds or illness during the campaign (disputed) |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: wounds or illness during the campaign (disputed) | Statement: [Battle of Diaoyu Castle, MöngkeCauseOfDeath, wounds or illness during the campaign (disputed)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MöngkeCauseOfDeath Context triple: [Battle of Diaoyu Castle, MöngkeCauseOfDeath, wounds or illness during the campaign (disputed)]
-
A.
monarchKilledInBattle
Indicates that a monarch died as a direct result of being killed during a battle.
-
B.
emperorKilled
Indicates that an emperor caused the death of another entity.
-
C.
diedDuringReignOf
Indicates that one entity died while another entity was in power or ruling.
-
D.
deifiedPersonDeathCause
Indicates the cause or manner of death of the person who is venerated or treated as a deity.
-
E.
endOfReignReason
chosen
Indicates the cause or circumstance that led to the termination of a ruler’s reign.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f0319b7c44819085736bcc256185e6 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f658ee40088190b71e1219407690d0 |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65760fd3081908ffe014a5e2bf069 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:27 a.m.